Hugging Face's logo

harsith05
/
imdbdata

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
harsith05 commited on
Commit
e78c518
·
verified ·
1 Parent(s): 6cba2fe

Training in progress, epoch 2, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +35 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9c36b6ccd06ef6f3eb7fd5bc05a6d5b59ac5bcf24bbab132ffd8c7697ec6932
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec7a44c4fb9a7cb89c58ea6e7b52ef4b9f0f88fac96ed45e44e84c487ccb991
3
  size 437958648
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31686a4203c6609e8e6d1cefe391345bfcedeb69e37b86938c4c18b48ee7ca0e
3
  size 15132
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c9bf082e97384ea8d78c1ae1a9a24272e120104f4220e2d417c3de66cf732b
3
  size 15132
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fde5d78d467270e6f38169a48e70e420d3afe1146078e423f8499685461bf22
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691b3b85e42c089d2bdb72309424d3454b990e0596c27b15f218b3f6e4c39e55
3
  size 14244
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:713ce80c4477b3cfcc8aacd01e948331f6b151bcde4f5963a683f54fa49aa3e3
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f9090a10451cfcde8a06c7be0e254fefb5188534b2f83a624ea5b7e7728345
3
  size 988
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08310ba03a71cba3080ae5cac15ca472b7eb75a918bf10a61ba4d46caf923ed7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c28abdc351c8a90f54e4f65c77f64d06f99dbfd78b3087ed5ba445ee81093fa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 1563,
3
- "best_metric": 0.6799984574317932,
4
- "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-1563",
5
- "epoch": 1.0,
6
  "eval_steps": 500,
7
- "global_step": 1563,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 92.052,
38
  "eval_steps_per_second": 5.755,
39
  "step": 1563
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 500,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 6515172397265280.0,
60
  "train_batch_size": 16,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
+ "best_global_step": 3126,
3
+ "best_metric": 0.6645415425300598,
4
+ "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-3126",
5
+ "epoch": 2.0,
6
  "eval_steps": 500,
7
+ "global_step": 3126,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 92.052,
38
  "eval_steps_per_second": 5.755,
39
  "step": 1563
40
+ },
41
+ {
42
+ "epoch": 1.2795905310300704,
43
+ "grad_norm": 1.741823673248291,
44
+ "learning_rate": 7.950786056049214e-06,
45
+ "loss": 0.6803,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 1.599488163787588,
50
+ "grad_norm": 1.358868956565857,
51
+ "learning_rate": 7.268626110731375e-06,
52
+ "loss": 0.6769,
53
+ "step": 2500
54
+ },
55
+ {
56
+ "epoch": 1.9193857965451055,
57
+ "grad_norm": 1.2229254245758057,
58
+ "learning_rate": 6.585099111414901e-06,
59
+ "loss": 0.6724,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 2.0,
64
+ "eval_loss": 0.6645415425300598,
65
+ "eval_runtime": 272.658,
66
+ "eval_samples_per_second": 91.69,
67
+ "eval_steps_per_second": 5.732,
68
+ "step": 3126
69
  }
70
  ],
71
  "logging_steps": 500,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 1.302353679597312e+16,
89
  "train_batch_size": 16,
90
  "trial_name": null,
91
  "trial_params": null